Article

Intelligence Through Interaction: Towards a Unified Theory for Learning

Authors:

Gail A. Carpenter,

Stephen GrossbergAuthors Info & Claims

ISNN '07: Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks

Pages 1094 - 1103

https://doi.org/10.1007/978-3-540-72383-7_128

Published: 03 June 2007 Publication History

Abstract

Machine learning, a cornerstone of intelligent systems, has typically been studied in the context of specific tasks, including clustering (unsupervised learning), classification (supervised learning), and control (reinforcement learning). This paper presents a learning architecture within which a universal adaptation mechanism unifies a rich set of traditionally distinct learning paradigms, including learning by matching, learning by association, learning by instruction, and learning by reinforcement. In accordance with the notion of embodied intelligence, such a learning theory provides a computational account of how an autonomous agent may acquire the knowledge of its environment in a real-time, incremental, and continuous manner. Through a case study on a minefield navigation domain, we illustrate the efficacy of the proposed model, the learning paradigms encompassed, and the various types of knowledge learned.

References

[1]

Anderson, M.L.: Embodied Cognition: A Field Guide. Artificial Intelligence 149 (2003) 91-130.

[2]

Carpenter, G. A., Grossberg, S.: A Massively Parallel Architecture for a Self- organizing Neural Pattern Recognition Machine. Computer Vision, Graphics, and Image Processing 37 (1987) 54-115.

[3]

Carpenter, G. A., Grossberg, S., editors: Pattern Recognition by Self-Organizing Neural Networks. Cambridge, MA: MIT Press (1991).

[4]

Carpenter, G. A., Grossberg, S., Rosen, D. B.: Fuzzy ART: Fast Stable Learning and Categorization of Analog Patterns by an Adaptive Resonance System. Neural Networks 4 (1991) 759-771.

[5]

Carpenter, G.A., Grossberg, S.: Adaptive Rresonance Theory. In M.A. Ar- bib, editor, The Handbook of Brain Theory and Neural Networks, 87-90. Cambridge, MA: MIT Press (2003).

[6]

Duda, R. O., Hart, P.E., Stock, D.G., editors. Pattern Classification (2nd edi- tion). New York: John Wiley, Section 10.11.2, (2001).

[7]

Gordan, D., Subramanian, D.: A Cognitive Model of Learning to Navigate. In Proceedings, Nineteenth Annual Conference of the Cognitive Science Society (1997) 271-276.

[8]

Grossberg, S.: Adaptive Pattern Recognition and Universal Recoding, I: Parallel Development and Coding of Neural Feature Detectors. Biological Cybernetics 23 (1976) 121-134.

[9]

Grossberg, S.: Adaptive Pattern Recognition and Universal Recoding, II: Feedback, Expectation, Olfaction, and Illusion. Biological Cybernetics 23 (1976) 187-202.

[10]

Grossberg, S.: How Does the Cerebral Cortex Work? Development, Learning, Attention, and 3d Vision by Laminar Circuits of Visual cortex. Behavioral and Cognitive Neuroscience Reviews 2 (2003) 47-76.

[11]

He, J., Tan, A-H., Tan, C-L: On Machine Learning Methods for Chinese Documents Classification. Applied Intelligence: Special Issue on Text and Web Mining 18 (3) (2003) 311-322.

[12]

Levine, D. S., editor: Introduction to Neural and Cognitive Modeling. New Jersey: Lawrence Erlbaum Associates, Chapter 6 (2000).

[13]

Raizada, R., Grossberg, S.: Towards a Theory of the Laminar Architecture of Cerebral Cortes: Computational Clues from the Visual System. Cerebral Cortex 13 (2003) 200-213.

[14]

Sun, R., Merrill, E., Peterson, T.: From Implicit Skills to Explicit Knowledge: A Bottom-up Model of Skill Learning. Cognitive Science 25 (2) (2001) 203-244.

[15]

Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. Cambridge, MA: MIT Press (1998).

[16]

Tan, A. H.: Adaptive Resonance Associative Map. Neural Networks 8 (3) (1995) 437-446.

[17]

Tan, A. H.: Cascade ARTMAP: Integrating Neural Computation and Symboli Knowledge Processing. IEEE Transactions on Neural Networks 8 (2) (1997) 237- 250.

[18]

Tan, A-H., Ong, H-L., Pan, H., Ng, J., Li, Q-X.: Towards Personalized Web Intelligence. Knowledge and Information Systems 6 (5) 595-616 (2004).

[19]

Tan, A-H., Soon, H.-S.: Predictive Adaptive Resonance Theory and Knowledge Discovery in Database. In Proceedings, Fourth Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD'00), Kyoto, pages (2000) 173-176.

[20]

Tan, A.H.: FALCON: A Fusion Architecture for Learning, Cognition, and Navigation. In Proceedings, International Joint Conference on Neural Networks (2004) 3297-3302.

[21]

Tan, A.H.: Self-organizing Neural Architecture for Reinforcement Learning. In Proceedings, J. Wang et al. (Eds.): International Symposium on Neural Networks (ISNN'06), Chengdu, China, LNCS 3971 (2006) 470-475.

[22]

Tan, A.H., Pan, H.: Predictive Neural Networks for Gene Expression Data Analysis. Neural Networks 18 (3) (2005) 297-306.

[23]

Tan, A.H., Lu, N., Xiao, D.: Integrating Temporal Difference Methods and Selforganizing Neural Networks for Reinforcement Learning with Delayed Evaluative feedback. IEEE Transactions on Neural Networks, to appear.

Cited By

Wai KGeng MPateria SSubagdja BTan ADastani MSichman JAlechina NDignum V(2024)Explaining Sequences of Actions in Multi-agent Deep Reinforcement Learning ModelsProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3663219(2537-2539)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3663219
Geng MPateria SSubagdja BTan A(2024)HiSOMAExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.124117252:PAOnline publication date: 24-Jul-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.124117
Švaco MJerbić BŠuligoj F(2018)ARTgrid: a two-level learning architecture based on adaptive resonance theoryAdvances in Artificial Neural Systems10.1155/2014/1854922014(11-11)Online publication date: 11-Dec-2018
https://dl.acm.org/doi/10.1155/2014/185492
Show More Cited By

Intelligence Through Interaction: Towards a Unified Theory for Learning
1. Computing methodologies

Recommendations

Prediction in Intelligence: An Empirical Comparison of Off-policy Algorithms on Robots
AAMAS '19: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems

The ability to continually make predictions about the world may be central to intelligence. Off-policy learning and general value functions (GVFs) are well-established algorithmic techniques for learning about many signals while interacting with the ...
Artificial Intelligence Making Machines Learn: A friendly Introduction
Transfer Learning and Intelligence: an Argument and Approach
Proceedings of the 2008 conference on Artificial General Intelligence 2008: Proceedings of the First AGI Conference

In order to claim fully general intelligence in an autonomous agent, the ability to learn is one of the most central capabilities. Classical machine learning techniques have had many significant empirical successes, but large real-world problems that ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image Guide Proceedings

ISNN '07: Proceedings of the 4th international symposium on Neural Networks: Advances in Neural Networks

June 2007

1352 pages

ISBN:9783540723820

Editors:
Derong Liu
Department of Electrical and Computer Engineering (M/C 154), University of Illinois at Chicago, Chicago, USA 60607-7053
,
Shumin Fei
School of Automation, Southeast University, Nanjing, China 210096
,
Zeng-Guang Hou
Laboratory of Complex Systems, Institute of Automation, Chinese Adacemy of Sciences, Beijing, P. R. China 100080
,
Huaguang Zhang
School of Information Science and Engineering, Northeast University, Shenyang, China
,
Changyin Sun
School of Electrical Engineering, Hohai University, Nanjing, China

Publisher

Springer-Verlag

Berlin, Heidelberg

Publication History

Published: 03 June 2007

Qualifiers

Article

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

22
Total Citations
View Citations
0
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 16 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Wai KGeng MPateria SSubagdja BTan ADastani MSichman JAlechina NDignum V(2024)Explaining Sequences of Actions in Multi-agent Deep Reinforcement Learning ModelsProceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems10.5555/3635637.3663219(2537-2539)Online publication date: 6-May-2024
https://dl.acm.org/doi/10.5555/3635637.3663219
Geng MPateria SSubagdja BTan A(2024)HiSOMAExpert Systems with Applications: An International Journal10.1016/j.eswa.2024.124117252:PAOnline publication date: 24-Jul-2024
https://dl.acm.org/doi/10.1016/j.eswa.2024.124117
Švaco MJerbić BŠuligoj F(2018)ARTgrid: a two-level learning architecture based on adaptive resonance theoryAdvances in Artificial Neural Systems10.1155/2014/1854922014(11-11)Online publication date: 11-Dec-2018
https://dl.acm.org/doi/10.1155/2014/185492
Wang DWu ETan A(2018)Analysis of Public Transportation Patterns in a Densely Populated City with Station-based Shared BikesProceedings of the 3rd International Conference on Crowd Science and Engineering10.1145/3265689.3265697(1-8)Online publication date: 28-Jul-2018
https://dl.acm.org/doi/10.1145/3265689.3265697
Subagdja BTan A(2018)Neural modeling of sequential inferences and learning over episodic memoryNeurocomputing10.1016/j.neucom.2015.02.038161:C(229-242)Online publication date: 31-Dec-2018
https://dl.acm.org/doi/10.1016/j.neucom.2015.02.038
Subagdja BTan A(2018)iFALCONNeurocomputing10.1016/j.neucom.2012.01.00886(124-139)Online publication date: 31-Dec-2018
https://dl.acm.org/doi/10.1016/j.neucom.2012.01.008
Subagdja BTan ASingh SMarkovitch S(2017)Towards a brain inspired model of self-awareness for sociable agentsProceedings of the Thirty-First AAAI Conference on Artificial Intelligence10.5555/3298023.3298213(4452-4458)Online publication date: 4-Feb-2017
https://dl.acm.org/doi/10.5555/3298023.3298213
Chang PTan A(2017)Encoding and recall of spatio-temporal episodic memory in real timeProceedings of the 26th International Joint Conference on Artificial Intelligence10.5555/3172077.3172094(1490-1496)Online publication date: 19-Aug-2017
https://dl.acm.org/doi/10.5555/3172077.3172094
Gao STan AJonker CMarsella SThangarajah JTuyls K(2016)An Autonomous Agent for Learning Spatiotemporal Models of Human Daily ActivitiesProceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems10.5555/2936924.2937206(1453-1454)Online publication date: 9-May-2016
https://dl.acm.org/doi/10.5555/2936924.2937206
Wang DTan AMiao CJonker CMarsella SThangarajah JTuyls K(2016)Modeling Autobiographical Memory in Human-Like Autonomous AgentsProceedings of the 2016 International Conference on Autonomous Agents & Multiagent Systems10.5555/2936924.2937048(845-853)Online publication date: 9-May-2016
https://dl.acm.org/doi/10.5555/2936924.2937048
Show More Cited By

View Options

View options

Media

Figures

Other

Tables

View Table of Contents